Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Humorous Image Captioning on Human Evaluation Dataset (test)
Loading...
1,554.6
Elo Rating
HUMORCHAIN
1,460.4384
1,484.8842
1,509.33
1,533.7758
Nov 21, 2025
Elo Rating
Bradley-Terry Score
Updated 4mo ago
Evaluation Results
Method
Method
Links
Elo Rating
Bradley-Terry Score
HUMORCHAIN
Strategy=Theory-Guided...
2025.11
1,554.6
3.57
Method F
Strategy=Few-shot + Ru...
2025.11
1,528.84
1
Method E
Strategy=Rule-Guided +...
2025.11
1,526.46
0.88
Method D
Strategy=Few-shot + Ru...
2025.11
1,505.43
0.73
Method C
Strategy=Rule-Based
2025.11
1,504.45
0.54
Method A
Strategy=Zero-shot
2025.11
1,498.09
0.52
Method B
Strategy=Few-shot
2025.11
1,495.05
0.46
OxfordTVG-HIC
Strategy=External Oxfo...
2025.11
1,467.4
0.55
CLoT
Strategy=Sun Yat-sen U...
2025.11
1,464.06
0.74
Feedback
Search any
task
Search any
task